US20050223005A1 - Shared file system cache in a virtual machine or LPAR environment - Google Patents

Shared file system cache in a virtual machine or LPAR environment Download PDF

Info

Publication number
US20050223005A1
US20050223005A1 US11147549 US14754905A US2005223005A1 US 20050223005 A1 US20050223005 A1 US 20050223005A1 US 11147549 US11147549 US 11147549 US 14754905 A US14754905 A US 14754905A US 2005223005 A1 US2005223005 A1 US 2005223005A1
Authority
US
Grant status
Application
Patent type
Prior art keywords
cache
lock
virtual machine
program
program function
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
US11147549
Other versions
US7831977B2 (en )
Inventor
Steven Shultz
Xenia Tkatschow
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/52Program synchronisation; Mutual exclusion, e.g. by means of semaphores
    • G06F9/526Mutual exclusion algorithms
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
    • G06F12/0806Multiuser, multiprocessor or multiprocessing cache systems
    • G06F12/084Multiuser, multiprocessor or multiprocessing cache systems with a shared cache
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • G06F2009/45566Nested virtual machines
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • G06F2009/45583Memory management, e.g. access, allocation

Abstract

Computer system, method and program for defining first and second virtual machines and a memory shared by the first and second virtual machines. A filesystem cache resides in the shared memory. A lock structure resides in the shared memory to record which virtual machine, if any, currently has an exclusive lock for writing to the cache. The first virtual machine includes a first program function to acquire the exclusive lock when available by manipulation of the lock structure, and a second program function active after the first virtual machine acquires the exclusive lock, to write to the cache. The lock structure is directly accessible by the first program function. The cache is directly accessible by the second program function. The second virtual machine includes a third program function to acquire the exclusive lock when available by manipulation of the lock structure, and a fourth program function active after the second virtual machine acquires the exclusive lock, to write to the cache. The lock structure is directly accessible by the third program function. The cache is directly accessible by the fourth program function. Another computer system, method and program is embodied in logical partitions of a real computer, instead of virtual machines.

Description

  • This is a Continuation-in-Part of U.S. Patent Application entitled “Management of Locks in a Virtual Machine Environment”, Ser. No. 10/425,468 filed Apr. 29, 2003 by Donovan et al.
  • BACKGROUND
  • The present invention relates generally to computer systems, and deals more particularly with a cache for virtual machines and logical partitions.
  • A virtual machine is a virtual sharing/partitioning of real resources such as real memory, CPU and I/O. A known virtual machine operating system includes a common base portion and separate user portions formed by the common base portion. In an IBM z/VM operating system, the common base portion is called the “Control Program” or “CP” and each user portion is called a “virtual machine” or “guest”. A guest operating system executes/runs on each virtual machine, and one or more applications run on the guest operating system. Each application and guest operating system operate as if they are running on their own private, real computer.
  • In some computing environments, resources are shared amongst multiple programs. Shared resources consist of shared data (including shared files and shared directories) and shared processing routines. For example, in IBM VM/370 shared data was stored in shared memory accessible by multiple virtual machines. Also, in IBM VM/CMS, some portions of memory private to the virtual machine are shared among multiple programs in the same virtual machine. VM/CMS uses private locks to determine when access to the shared memory can be parallel and when such access must be sequential. Also in VM/CMS, there are processing routines private to the virtual machine which all programs in the same virtual machine use to access external storage mediums. VM/CMS uses private locks to determine when shared processing routines can be executed in parallel and when such routines must be executed sequentially. While VM/CMS is effective in sharing resources, it is limited to sharing resources within a single virtual machine.
  • In IBM VM/SP6 operating system and subsequent releases of IBM VM/ESA and IBM z/VM operating systems, data to be shared amongst multiple virtual machines (with a common base portion) resides in private memory of one server virtual machine. Likewise, a lock management structure resides in the server virtual machine. This data is shared by multiple virtual machines by requiring all virtual machines to communicate with the server virtual machine to request access to the shared data. Such communication is in the form of TCP/IP, IUCV or Guest LAN messages (described below), which require significant overhead. The server virtual machine then uses its private locks to arbitrate access to the shared data. A similar arrangement is used to arbitrate the use of shared processing routines. While the foregoing arrangement provides access by multiple virtual machines to shared resources, it requires a significant overhead communication protocol between the requesting virtual machines and the server virtual machine.
  • In general, a cache is a high speed, limited capacity semiconductor memory such as RAM, which contains portions or pages of data stored on relatively slow access, magnetic disk. There are many known algorithms for determining which pages to retain in cache; however, typically, the least recently used pages are outpaged to storage to make room for new pages requested to be updated/written or read by a program. Because a program will typically perform multiple operations on a single page while resident in cache, the cache improves overall reading and writing speed. Thus, the combination of a cache and disk storage provide high speed access and large capacity storage.
  • Nonshared filesystem caches are known for both shared and nonshared files.
  • It was known for two different applications in the same real computer or the same virtual machine to share a read/write cache in memory for files stored in high capacity storage.
  • In a virtual machine environment, it was known to provide nonshared (i.e. private to/accessible by respective virtual machines or specific programs in each virtual machine) read/write caches in nonshared RAM for nonshared files in external (disk) storage. It was also known from U.S. Pat. No. 6,075,938 to provide a shared (i.e. shared by/accessible by multiple virtual machines and their programs) read-only cache in RAM for shared files in external (disk) storage.
  • It was known for a file system to store both file system data and file system metadata. The metadata comprises information about the file system data, such as a directory/hierarchy of files in the file system to locate a file of interest, size of file, etc. It was known to provide a nonshared cache for both file system data and file system metadata.
  • Logical partitions (“LPARs”) are also known today within a real computer. An LPAR is a logical partitioning of the real resources, i.e. CPU, RAM, etc. The CPU is logical partitioned by allocated time slices to respective LPARs. The RAM is logically partitioned by dividing the memory between the different partitions.
  • It was known for two different applications in the same LPAR to share a read/write cache in memory for files stored in high capacity storage.
  • A general object of the present invention is to provide a shared, read/write filesystem cache for high capacity storage in a virtual machine environment.
  • Another general object of the present invention is to provide a shared, read/write filesystem cache for high capacity storage in an LPAR environment.
  • Another object of the present invention is to provide such read/write filesystem caches in an effective and efficient manner.
  • SUMMARY OF THE INVENTION
  • The invention resides in a computer system, method and program for defining first and second virtual machines and a memory shared by the first and second virtual machines. A filesystem cache resides in the shared memory. A lock structure resides in the shared memory to record which virtual machine, if any, currently has an exclusive lock for writing to the cache. The first virtual machine includes a first program function to acquire the exclusive lock when available by manipulation of the lock structure, and a second program function active after the first virtual machine acquires the exclusive lock, to write to the cache. The lock structure is directly accessible by the first program function. The cache is directly accessible by the second program function. The second virtual machine includes a third program function to acquire the exclusive lock when available by manipulation of the lock structure, and a fourth program function active after the second virtual machine acquires the exclusive lock, to write to the cache. The lock structure is directly accessible by the third program function. The cache is directly accessible by the fourth program function.
  • The invention resides in a computer system, method and program for defining first and second logical partitions and a memory shared by the first and second logical partitions. A filesystem cache resides in the shared memory. A lock structure resides in the shared memory to record which logical partition, if any, currently has an exclusive lock for writing to the cache. The first logical partition includes a first program function to acquire the exclusive lock when available by manipulation of the lock structure, and a second program function active after the first logical partition acquires the exclusive lock, to write to the cache. The lock structure is directly accessible by the first program function. The cache is directly accessible by the second program function. The second logical partition includes a third program function to acquire the exclusive lock when available by manipulation of the lock structure, and a fourth program function active after the second logical partition acquires the exclusive lock, to write to the cache. The lock structure is directly accessible by the third program function. The cache is directly accessible by the fourth program function.
  • BRIEF DESCRIPTION OF THE FIGURES
  • FIG. 1 is a block diagram of a computer system including a virtual machine operating system with a shared read/write filesystem cache, data access functions (“DAFs”), lock access functions (“LAFs”) and cache access functions (“CAFs”) for respective virtual machines, according to a first embodiment of the present invention.
  • FIG. 2 is a flow chart illustrating a write operation utilizing the shared cache, DAFs, LAFS and CAFs of FIG. 1.
  • FIG. 3 is a flow chart illustrating a read operation utilizing the shared cache, DAFs, LAFS and CAFs of FIG. 1.
  • FIG. 4 is a block diagram of the computer system of FIG. 1 illustrating in more detail the LAFs (in one example/scenario) used for the DAFs and CAFs of FIG. 1-3.
  • FIG. 5 is a flow chart illustrating the LAFS, DAFs and CAFs of FIG. 4.
  • FIG. 6 is a block diagram of another computer system logically divided into LPARs with a shared read/write filesystem cache, data access functions (“DAFs”), lock access functions (“LAFs”) and cache access functions (“CAFs”) for respective LPARs, according to a second embodiment of the present invention.
  • DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
  • The present invention will now be described in detail with reference to the drawings, where like reference numbers indicate like elements. FIG. 1 illustrates a computer system generally designated 10 according to an embodiment of the present invention. Computer system 10 includes a physical computer 20 (which includes a CPU 23, semiconductor memory/RAM 30 and disk storage 59) and a virtual machine operating system 11. By way of example, the virtual machine operating system can be IBM z/VM version 4.2.0 or 4.3.0 modified to include the present invention. The details of z/VM 4.2.0 are disclosed in IBM publication “z/VM 4.2.0 General Information” (Document Number: GC24-5991-03) which is available from International Business Machines Corp. at PO Box 29570, IBM Publications, Raleigh, N.C. 27626-0570 or on the WWW at www.IBM.com/shop/publications/order. This publication is hereby incorporated by reference as part of the present disclosure. Operating system 11 executes in the physical computer 10 such as an IBM zSeries server although the present invention can be implemented in other server computers or personal computers as well. Operating system 11 includes a common base portion 21 (called “CP” in the z/VM operating system). Common base portion 21 logically partitions the resources (including the CPU and memory) of the physical computer to form user portions or virtual machines 12, 14 and 16. In these logical partitions, the each virtual machine has a “virtual CPU”, i.e. a time-slice portion of the real CPU(s) that appears to the guest operating system as its own CPU. The common base portion also performs functions such as virtualizing memory, virtualizing devices and virtualizing CPUs. Guest operating systems 22, 24 and 26 execute on virtual machines 12, 14 and 16, respectively, and applications 32, 34 and 36 execute on guest operating systems 22, 24 and 26 respectively. There may be multiple applications executing on each operating system. By way of example, guest operating systems 22 and 24 are the Linux (TM of Linus Torvalds) operating system, and guest operating system 26 is an IBM CMS operating system. Other guest operating systems executing on virtual machines are also feasible such as Microsoft Windows (tm) operating system, Unix (tm) operating system, Sun Microsystems Solaris (tm) operating system or Hewlett Packard HP UX operating system. By way of example, applications 32, 34 and 36 can be IBM DB2 data base management application, IBM WebSphere application, communications applications, etc. The nature of applications 32, 34 and 36 forrn no part of the present invention, except that they may request to access shared files in storage 59 via shared filesystem cache 51. As explained in more detail below, shared read/write filesystem cache 51 stores a limited number of portions or “pages” of shared filesystem data and metatdata (data describing the topology of the filesystem) stored in storage 59 so the programs within virtual machines 12, 14 and 16 can rapidly access these file portions or pages for reading and writing.
  • Each virtual machine has its own private memory in nonshared memory area 27 (typically semiconductor RAM) for its private data, applications and operating system program functions such as Cache Access Functions (“CAFs”) 52, 54, and 56, Data Access Functions (“DAFs”) 62, 64 and 66 and Lock Access Functions (“LAFs”) 72, 74 and 76 in virtual machines 12, 14 and 16, respectively. Consequently, each virtual machine is afforded a measure of privacy from the other virtual machines as in separate physical computers.
  • Computer 10 also includes a shared memory area 25 (typically semiconductor RAM) which is shared by all of the virtual machines 12, 14 and 16. (RAM provides very fast access, much faster than access to disk storage.) Being “shared” each virtual machine 12, 14 and 16 can directly access the shared memory 25 and its shared data and shared data structures by appropriate address. The shared data structures include shared filesystem cache 51 and shared lock structure (or control block) 58. By way of example, the disk storage 59 may comprise hundreds or thousands of megabytes, gigabytes or terabytes or more (the available disk capacity tends to grow every year), and the shared filesystem cache 51 may have a small fraction of this capacity, for example, tens of megabytes or even a hundred megabyte (cache capacity may grow with new computers every year) The shared filesystem cache 51 includes shared cached file data 53 and shared cached file system metadata 55. The shared cached file data 53 comprises cached portions or “pages” of file data stored on external disk (or other, high capacity) storage 59. The shared cached file system metadata 55 comprises cached portions or pages of metadata stored on external disk storage 59. The metadata comprises information about the file data, such as a directory/hierarchy of files in a file system to locate a file of interest, size of file, etc. Each file system generates the metadata for the files in its system. The operating system in each virtual machine may include a file system program function, the file system program can be a separate application executing in each virtual machine or there can be one file system program for the entire real computer or common base portion. The single file system program (for the entire real computer) is typically used for files to be shared amongst different virtual machines. All the virtual machines 12, 14 and 16 (and their programs 22, 32, 24, 34, 26 and 36) can read from and write to the shared filesystem cache 51 to read from and write to the shared cached file data 53 and shared cache file system metadata 55. Within each virtual machine 12, 14 and 15, a respective DAF 62, 64 and 66 manages the read and write requests (made by programs 22, 32, 24, 34, 26 and 36) to the shared filesystem cache 51, a respective LAF 72, 74 and 76 obtains the requisite lock for the shared filesystem cache 51 (to permit synchronized reading and writing in a shared environment) and a respective CAF 52, 54 and 56 outpage from and inpage to the shared cache 51 as needed. (There can also be other shared data 78, included shared files and a shared directory, within shared memory 25.) A shared lock data structure 58 which records holder of and waiters for the locks, also resides in shared memory 25. LAFs 72, 74 and 76 access and manage the shared lock data structure 58 to obtain or release a lock for the shared data in shared cache 51. Each of the LAFs abides by the records of the shared lock structure. CAFs 52, 54 and 56, DAFs 62, 62 and 66 and LAFs 72, 74 and 76 access the shared filesystem cache 51, shared data 78 and shared lock 58 pursuant to read and write requests made by their respective applications 32, 34 and 36 and their respective operating systems 22, 24 and 26.
  • In the state illustrated in FIG. 1 (which is an example of a situation in the present invention), virtual machines 12 and 16 are concurrently reading cache file data 53 and associated cached filesystem metadata 55 from shared filesystem cache 51, and virtual machine 14 is waiting to write new cache file data and new cached filesystem metadata to shared filesystem cache 51. As explained below, virtual machine 14 cannot write to shared filesystem cache 51 until virtual machines 12 or 16 conclude their access to the shared filesystem cache 51 and relinquish their lock, because a write operation would alter the cache file data and metadata being read by virtual machines 12 and 16. In the case of virtual machine 12, the read request 92 originated from application 32 which passed it to operating system 22 for execution. Likewise, in the case of virtual machine 16, the read request 94 originated from application 36 which passed it to operating system 26 for execution. In the case of virtual machine 14, the write request originated from operating system 24. However, the source of the read and write request within each virtual machine is not important to the present invention; the foregoing is just an example.
  • FIG. 2 illustrates operation of each LAF, CAF and DAF when the respective virtual machine initiates writing to shared filesystem cache 51. The following iteration of the steps of FIG. 2 is one possible scenario of the LAFs, CAFs and DAFs, for purposes of explanation. In step 200, application 34 within the virtual machine 14 invokes DAF 64 (within operating system 24) to request a write to the shared filesystem cache 51. In response, DAF 64 invokes LAF 74 (within operating system 24) to obtain an exclusive/write lock for the shared cache 51. In response, LAF 74 checks shared lock structure 58 for the exclusive/write lock for the shared cache 51 (step 202). The process by which LAF 73 obtains the exclusive/write lock is described in more detail below with reference to FIGS. 4 and 5. The exclusive/write lock will not be available if there is a current holder of any type of lock on shared filesystem cache 51 and/or if there are pending requests for a lock on a lock wait queue ahead of the request of DAF 54. When LAF 74 obtains the exclusive/write lock for the shared filesystem cache 51, LAF 74 notifies DAF 64. Then, DAF 64 reads the cached filesystem metadata 55 to determine if the file portion or “page” to which application 34 wants to update/write currently resides in shared filesystem cache 51 as a page of cached file data 53 (step 204). If not (decision 206, no branch), then DAF 64 invokes CAF 54 to outpage the least recently used (“LRU”) page (i.e. both the LRU cached file data page and cached filesystem metadata for the LRU page) from shared filesystem cache 51 to storage 59 (step 210). Next, CAF 54 allocates a page in shared filesystem cache 51 for both the new cached file data to be written and the associated filesystem metadata (step 212). After step 212, CAF 54 returns to DAF 64 which updates/writes the new file data and associated metadata of application 34 to the shared filesystem cache 51 (step 214). Referring back to decision 106 yes, branch, for the case where the page of file data to be updated/written and associated filesystem metadata resided in shared filesystem cache 51 when checked in step 204 (decision 206, yes branch), then DAF 64 updates/writes this page of the cached file data as well as the associated metadata in step 214. This completes the write operation requested by application 34. Next, CAF 54 determines if it is time to flush the entire contents of shared filesystem cache 51 to storage 59 (decision 216). There are a variety of well known algorithms and events that can trigger such flushing, for example, time-out of a timer, synchronization of a filesystem or checking the filesystem for inconsistencies. If so, then CAF 54 writes the entire contents of shared filesystem cache 51 to storage (step 220). If not, then CAF 54 invokes LAF 74 to relinquish CAF 54's exclusive/ write lock (step 222).
  • FIG. 3 illustrates operation of each LAF, CAF and DAF when the respective virtual machine initiates reading from shared filesystem cache 51. The following iteration of the steps of FIG. 4 is one possible scenario of the LAFs, CAFs and DAFs, for purposes of explanation. In step 300, application 32 within the virtual machine 12 invokes DAF 62 (within operating system 22) to request to read from the shared filesystem cache 51. In response, DAF 62 invokes LAF 72 to obtain a nonexclusive lock for the shared cache 51. In response, LAF 72 checks shared lock structure 58 for the nonexclusive lock for the shared filesystem cache 51 (step 302). The process by which LAF 72 obtains the nonexclusive lock is described in more detail below with reference to FIGS. 4 and 5. The nonexclusive lock will be available immediately if there is no program currently with an exclusive/write lock or waiting in the lock wait queue for an exclusive/write lock. If there is such a program(s), then LAF 72 will obtain the nonexclusive lock after such program(s) relinquish their exclusive/write lock. When LAF 72 obtains the nonexclusive lock for the shared filesystem cache 51, LAF 72 notifies DAF 62. Then, DAF 62 requests to read the cached filesystem metadata 55 to determine if the file portion/page which application 32 wants to read currently resides in cached file data 53 (step 304). If not (decision 306, no branch), then DAF 62 invokes LAF 72 to obtain an exclusive write lock for shared filesystem cache 51 (step 307). The purpose of the exclusive write lock is to allow outpaging from the shared cache. After obtaining the shared write lock, LAF 52 returns to DAF 62 which invokes CAF 52 to outpage the least recently used (“LRU”) page (i.e. both the LRU cached file data page and cached filesystem metadata for the LRU page) from shared filesystem cache 51 to storage 59 to make room for the requested page to be read (step 310). Next, CAF 52 allocates a page (location) in shared filesystem cache 51 for both the new cached file data to be read and the associated filesystem metadata, and reads the requested page of file data and associated metadata from storage 59 into shared filesystem cache 51 (step 312). After CAF 52 returns to DAF 62, DAF 62 invokes LAF 72 to relinquish the exclusive write lock on shared filesystem cache 51, and then LAF 72 returns to DAF 62 (step 313). After step 313, DAF 62 reads the requested page of file data and associated metadata from the shared filesystem cache 51 for application 32 (step 314). Referring back to decision 306 yes, branch, for the case where the page of file data to be read and associated filesystem metadata resided in shared filesystem cache 51 when checked in step 304 (decision 306, yes branch), then DAF 62 reads this page of the cached file data as well as the associated metadata in step 314. After step 314, DAF 62 invokes CAF 52 to determine if it is time to flush the entire contents of shared cache 51 to storage 59 (decision 316). There are a variety of well known algorithms and events that can trigger such flushing, for example, time-out of a timer, synchronization of a filesystem or checking the filesystem for inconsistencies. If so (decision 316, yes branch), then CAF 52 writes the entire contents of shared filesystem cache 51 to storage (step 320). After step 320, or if it is not time to flush shared filesystem cache 51, then CAF 52 invokes LAF 72 to relinquish CAF 52's nonexclusive lock (step 322).
  • FIG. 4 illustrates the lock data structure (or control block) 58 within the shared memory 25 of computer system 10 in more detail. FIG. 4 also illustrates figuratively by lock chain 90 and associated arrows to the virtual machines, the lock wait queue within the lock structure 58. In the illustrated example, both virtual machines 12 and 16 concurrently hold a nonexclusive (read) lock 91 for shared cache 51. Virtual machine 14 has a place holder 92 waiting on virtual machines 12 and 16 for an exclusive (write) lock to shared filesystem cache 51. This is actually recorded in lock structure or control block 58 which indicates that virtual machines 12 and 16 concurrently hold a nonexclusive lock for shared filesystem cache 51 and virtual machine 14 is waiting on virtual machines 12 and 16 for an exclusive lock for shared filesystem cache 51. The “waiter list” 95 of control block 58 indicates the foregoing ownership of the lock, order of the waiter(s), and the nature of each lock, i.e. virtual machines 12 and 16 currently hold lock 91 in a (nonexclusive) shared manner, and virtual machine 14 is currently waiting for the lock in an exclusive manner. Although not shown in FIG. 4, there is a similar lock structure for shared data 78, i.e. other shared files and shared directory, in shared memory 25.
  • FIG. 5 illustrates steps 202 and 202 (and other steps as indicated below) performed by each LAF in response to requests by the respective DAF to obtain the lock for shared filesystem cache 51. (Similar steps occur when each DAF attempts to obtain a lock for other shared data 78 and then access this other shared data 78.) In the following example, a virtual machine 12, 14 or 16 requests a lock for shared cache 51 (step 701). If the virtual machine just wants to read the shared filesystem cache (such as the foregoing example of virtual machines 12 and 16), then the virtual machine need only request a nonexclusive lock. However, if the virtual machine wants to write to the shared filesystem cache (such as the foregoing example of virtual machine 14), then the virtual machine will request an exclusive/write lock. If the request is for an exclusive/write lock, then decision 702 leads to decision 704. In decision 704, the LAF determines if the requested exclusive lock is currently held by another virtual machine (either in a shared or exclusive manner). If so, the exclusive lock is not available to the current requester, and the LAF updates the control block 58 to indicate that the requesting virtual machine is on the “waiter list” and is registered on the wait queue (step 705). Next, the LAF determines if its virtual machine has other work to do (decision 706). If not, then the LAF makes an entry in control block 58 under the category of “status” to indicate that the requesting virtual machine is “idle” (step 708). Then, the LAF causes the requesting virtual machine to enter into the “idle/quiescent” state after making an entry in another control block that this virtual machine is programmed to read when it awakens (step 710). Then, the requesting virtual machine waits for an interrupt (decision 712), at which point it will awaken and read the other control block. This other control block notifies the virtual machine to invoke its LAF (step 713). Referring again to decision 706, if the requesting virtual machine (that cannot get the lock now) has other work to do, the LAF will return control to the guest operating system or application to perform that other work (step 707). Afterwards, the guest operating system will call the LAF (step 713).
  • When the LAF is called in step 713 via either decision 712 or step 707, the LAF will read control block 58 to determine if its virtual machine is eligible to hold the lock, i.e. if the requested lock is exclusive, that no other virtual machine currently holds the lock, or if the requested lock is shared, that no other virtual machine currently holds the lock in an exclusive manner (decision 715). If the virtual machine is not eligible to hold the lock, then the LAF returns to decision 706 to continue processing as described above. However, if the virtual machine is now eligible to hold the lock, then the LAF acquires the lock (step 722). The acquisition of the lock is accomplished by corresponding update to control block 58, i.e. indication that the requesting virtual machine now holds the lock and is not a waiter. Next, the LAF invokes the DAF of the requesting virtual machine to directly access the shared cache 51 by appropriate address to determine if the shared filesystem cache 51 currently contains the page of interest (step 723/decision 206 or 306). If so, the DAF will read from or write to the cached file data and cached filesystem metadata in shared filesystem cache 51 (step 724/step 214 or 314). If not, the DAF will invoke the CAF to outpage the least recently used page and then inpage the requested page (step 723/steps 210, 212 or 310/312). Afterwards, the CAF notifies the LAF that the virtual machine has completed its access to the shared filesystem cache 51, and in response, the LAF “releases” the lock (step 728/step 222 or 322). In response, the LAF updates the control block 58 to indicate that the requesting virtual machine no longer holds the lock. Also, the LAF determines from the control block 58 if any other virtual machine is currently waiting for the lock (decision 730). If not, the processing of the LAF is complete and control is returned to the guest operating system or application of the LAF's virtual machine (step 732). If so, the LAF determines from the control block 58 if the first virtual machine marked “waiting” is “idle” (decision 734). If not, the LAF makes an entry in another control block that the non idle, waiting virtual machine will check when it completes its current work item (step 736). This entry will notify the waiting virtual machine (step 713) to invoke its LAF to attempt to acquire the lock at step 722. Then, processing is complete for the LAF (step 732) because it would be too disruptive to the non idle, waiting virtual machine to be interrupted at this time. Referring again to decision 734, if the waiting virtual machine is idle, then the LAF makes the entry in the other control block to invoke the LAF of the waiting virtual machine when interrupted, and issues an interrupt to the waiting virtual machine (step 738). This will not be disruptive to the waiting virtual machine because it is idle anyway. Then, the LAF of the requesting virtual machine completes its processing and returns control to the operating system or application of its own virtual machine (step 732). After receiving the interrupt, the idle, waiting virtual machine (step 712) will awaken and can acquire the lock at step 722.
  • Referring again to decision 704, if the requested lock is not currently held by anyone, then the LAF marks the requesting virtual machine as “not idle” in the “status” category of control block 58 (step 720) and grants the lock to the requesting virtual machine (step 722). The LAF continues processing as described above. Referring again to decision 702, if the lock requested by the virtual machine is shared, such as to read the shared cache 51, then the LAF determines if the lock is currently being held in an exclusive manner (decision 740). If not (i.e. no lock is currently being held or only a nonexclusive lock is currently being held), then the LAF proceeds to step 720 and continues processing as described above. However, if the lock is currently held in an exclusive manner by another virtual machine, then the LAF proceeds to step 705 to add the requesting virtual machine to the waiter list, and then continues as described above.
  • Each of the operating systems 22, 24, and 26 including their DAFs, LAFs and CAFs can be loaded into computer 20 from a computer storage medium such as magnetic or optic disk, magnetic tape, DVD, etc. or downloaded from network medium such as the Internet via a TCP/IP adapter card. Both the computer storage medium and network medium are collectively called computer readable medium.
  • FIG. 6 illustrates another embodiment of the present invention generally designated as computer system 111 where operating systems 22,24,26 with their CAFs 52,54,56, DAFs 62,64,66 and LAFs 72,74,76 execute in LPARs 112, 114, 116, respectively, instead of in virtual machines 12,14,16 as in the embodiment of FIG. 1. The LPARs 112,114,116 access the same type of shared memory 25 with the same type of shared filesystem cache 51 in the same manner as do virtual machines 12,14,16 in the embodiment of FIG. 1. The flow charts and flow diagrams of FIG. 2-4 apply to computer system 111 (as well as computer system 11), except the term “LPAR” is substituted for the term “virtual machine” when illustrating operation of CAFs 52,54,56, DAFs 62,64,66 and LAFs 72,74,76 in LPARs 112, 114, 116.
  • Each of the operating systems 22, 24, and 26 including their DAFs, LAFs and CAFs (in both the virtual machine and LPAR environments) can be loaded into computer 20 from a computer storage medium such as magnetic or optic disk, magnetic tape, DVD, etc. or downloaded from network medium such as the Internet via a TCP/IP adapter card. Both the computer storage medium and network medium are collectively called computer readable medium (which also encompasses the private memory which stores CAFs 52,54,56, DAFs 62,64,66 and LAFs 72,74,76 after being loaded into the computer systems.)
  • Based on the foregoing, computer systems, method and program products embodying the present invention has been disclosed. However, numerous modifications and substitutions can be made without deviating from the scope of the present invention. Therefore, the present invention has been disclosed by way of illustration and not limitation, and reference should be made to the following claims to determine the scope of the present invention.

Claims (20)

  1. 1. A computer system defining first and second virtual machines and a memory shared by said first and second virtual machines, said computer system comprising:
    a filesystem cache in said shared memory;
    a lock structure in said shared memory to record which virtual machine, if any, currently has an exclusive lock for writing to said cache;
    said first virtual machine includes a first program function to acquire said exclusive lock when available by manipulation of said lock structure, and a second program function active after said first virtual machine acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said first program function, said cache being directly accessible by said second program function; and
    said second virtual machine includes a third program function to acquire said exclusive lock when available by manipulation of said lock structure, and a fourth program function active after said second virtual machine acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said third program function, said cache being directly accessible by said fourth program function.
  2. 2. A system as set forth in claim 1 further comprising said storage.
  3. 3. A system as set forth in claim 1 wherein said shared filesystem cache stores both file data and associated directory data.
  4. 4. A system as set forth in claim 1 wherein said first and second program functions reside in a memory private to said first virtual machine such that said second virtual machine cannot invoke said first or second program functions, and said third and fourth program functions reside in a memory private to said second virtual machine such that said first virtual machine cannot invoke said third or fourth program functions.
  5. 5. A computer system as set forth in claim 1 wherein said first program function is initiated to acquire said lock by a request from a first application within said first virtual machine to write to a file in said storage, and said third program function is initiated to acquire said lock by a request from a second application within said second virtual machine to write to said file.
  6. 6. A computer system as set forth in claim 1 wherein said lock structure also records which virtual machine, if any, is currently waiting for said exclusive lock for writing to said cache.
  7. 7. A system as set forth in claim 1 wherein:
    said lock structure also records which virtual machine, if any, currently has a nonexclusive lock for reading from said cache;
    said first program function can acquire said nonexclusive lock when available by manipulation of said lock structure, and said second program function is active after said first virtual machine acquires said nonexclusive lock to read from said cache; and
    said third program function can acquire said nonexclusive lock when available by manipulation of said lock structure, and said fourth program function is active after said second virtual machine acquires said nonexclusive lock to read from said cache.
  8. 8. A computer system as set forth in claim 7 wherein both said first and second virtual machines can concurrently hold said nonexclusive lock.
  9. 9. A computer system as set forth in claim 7 wherein said lock structure also records which virtual machine, if any, is currently waiting for said nonexclusive lock for reading from said cache.
  10. 10. A computer system as set forth in claim 1 further comprising:
    a fifth program function, active after said first virtual machine acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said first virtual machine and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said fifth program function; and
    a sixth program function, active after said second virtual machine acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said second virtual machine and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said sixth program function.
  11. 11. A computer program product for execution within a computer system defining first and second virtual machines and a memory shared by said first and second virtual machines, said computer program product comprising:
    a computer readable medium;
    first program instructions to define a filesystem cache in said shared memory;
    second program instructions to define a lock structure in said shared memory to record which virtual machine, if any, currently has an exclusive lock for writing to said cache;
    third program instructions for execution in said first virtual machine to acquire said exclusive lock when available by manipulation of said lock structure, and fourth program instructions for execution in said first virtual machine active after said first virtual machine acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said third program function, said cache being directly accessible by said fourth program function; and
    fifth program instructions for execution in said second virtual machine to acquire said exclusive lock when available by manipulation of said lock structure, and sixth program instructions for execution in said second virtual machine active after said second virtual machine acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said fifth program instructions, said cache being directly accessible by said sixth program instructions; and wherein
    said first, second, third, fourth, fifth and sixth program instructions are stored on said medium.
  12. 12. A computer program product as set forth in claim 11 further comprising:
    seventh program instructions for execution in said first virtual machine active after said first virtual machine acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said first virtual machine and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said fifth program function; and
    eighth program instructions for execution in said second virtual machine, active after said second virtual machine acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said second virtual machine and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said sixth program function; and wherein
    said seventh and eighth program instructions are stored on said medium.
  13. 13. A computer system defining first and second logical partitions and a memory shared by said first and second logical partitions, said computer system comprising:
    a filesystem cache in said shared memory;
    a lock structure in said shared memory to record which logical partition, if any, currently has an exclusive lock for writing to said cache;
    said first logical partition includes a first program function to acquire said exclusive lock when available by manipulation of said lock structure, and a second program function active after said first logical partition acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said first program function, said cache being directly accessible by said second program function; and
    said second logical partition includes a third program function to acquire said exclusive lock when available by manipulation of said lock structure, and a fourth program function active after said second logical partition acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said third program function, said cache being directly accessible by said fourth program function.
  14. 14. A system as set forth in claim 13 wherein said shared filesystem cache stores both file data and associated directory data.
  15. 15. A system as set forth in claim 13 wherein said first and second program functions reside in a memory private to said first logical partition such that said second logical partition cannot invoke said first or second program functions, and said third and fourth program functions reside in a memory private to said second logical partition such that said first logical partition cannot invoke said third or fourth program functions.
  16. 16. A computer system as set forth in claim 13 wherein said first program function is initiated to acquire said lock by a request from a first application within said first logical partition to write to a file in said storage, and said third program function is initiated to acquire said lock by a request from a second application within said second logical partition to write to said file.
  17. 17. A system as set forth in claim 13 wherein:
    said lock structure also records which logical partition, if any, currently has a nonexclusive lock for reading from said cache;
    said first program function can acquire said nonexclusive lock when available by manipulation of said lock structure, and said second program function is active after said first logical partition acquires said nonexclusive lock to read from said cache; and
    said third program function can acquire said nonexclusive lock when available by manipulation of said lock structure, and said fourth program function is active after said second logical partition acquires said nonexclusive lock to read from said cache.
  18. 18. A computer system as set forth in claim 13 further comprising:
    a fifth program function, active after said first logical partition acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said first logical partition and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said fifth program function; and
    a sixth program function, active after said second logical partition acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said second logical partition and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said sixth program function.
  19. 19. A computer program product for execution within a computer system defining first and second logical partitions and a memory shared by said first and second logical partitions, said computer program product comprising:
    a computer readable medium;
    first program instructions to define a filesystem cache in said shared memory;
    second program instructions to define a lock structure in said shared memory to record which logical partition, if any, currently has an exclusive lock for writing to said cache;
    third program instructions for execution in said first logical partition to acquire said exclusive lock when available by manipulation of said lock structure, and fourth program instructions for execution in said first logical partition active after said first logical partition acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said third program function, said cache being directly accessible by said fourth program function; and
    fifth program instructions for execution in said second logical partition to acquire said exclusive lock when available by manipulation of said lock structure, and sixth program instructions for execution in said second logical partition active after said second logical partition acquires said exclusive lock, to write to said cache, said lock structure being directly accessible by said fifth program instructions, said cache being directly accessible by said sixth program instructions; and wherein
    said first, second, third, fourth, fifth and sixth program instructions are stored on said medium.
  20. 20. A computer program product as set forth in claim 19 further comprising:
    seventh program instructions for execution in said first logical partition active after said first logical partition acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said first logical partition and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said fifth program function; and
    eighth program instructions for execution in said second logical partition, active after said second logical partition acquires said exclusive lock, to outpage from said cache to storage when needed to make room for a page requested to be written by said second logical partition and to inpage said requested page from said storage when not resident in said cache, said cache being directly accessible by said sixth program function; and wherein
    said seventh and eighth program instructions are stored on said medium.
US11147549 2002-10-24 2005-06-07 Shared file system cache in a virtual machine or LPAR environment Active 2027-08-01 US7831977B2 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US10425468 US7328437B2 (en) 2002-10-24 2003-04-29 Management of locks in a virtual machine environment
US11147549 US7831977B2 (en) 2003-04-29 2005-06-07 Shared file system cache in a virtual machine or LPAR environment

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US11147549 US7831977B2 (en) 2003-04-29 2005-06-07 Shared file system cache in a virtual machine or LPAR environment
US12848186 US8589937B2 (en) 2003-04-29 2010-08-01 Shared file system cache in a virtual machine or LPAR environment

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US10425468 Continuation-In-Part US7328437B2 (en) 2002-10-24 2003-04-29 Management of locks in a virtual machine environment

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US12848186 Continuation US8589937B2 (en) 2002-10-24 2010-08-01 Shared file system cache in a virtual machine or LPAR environment

Publications (2)

Publication Number Publication Date
US20050223005A1 true true US20050223005A1 (en) 2005-10-06
US7831977B2 US7831977B2 (en) 2010-11-09

Family

ID=33415918

Family Applications (2)

Application Number Title Priority Date Filing Date
US11147549 Active 2027-08-01 US7831977B2 (en) 2002-10-24 2005-06-07 Shared file system cache in a virtual machine or LPAR environment
US12848186 Active 2023-07-26 US8589937B2 (en) 2002-10-24 2010-08-01 Shared file system cache in a virtual machine or LPAR environment

Family Applications After (1)

Application Number Title Priority Date Filing Date
US12848186 Active 2023-07-26 US8589937B2 (en) 2002-10-24 2010-08-01 Shared file system cache in a virtual machine or LPAR environment

Country Status (2)

Country Link
US (2) US7831977B2 (en)
JP (1) JP4012517B2 (en)

Cited By (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050132363A1 (en) * 2003-12-16 2005-06-16 Vijay Tewari Method, apparatus and system for optimizing context switching between virtual machines
US20070089111A1 (en) * 2004-12-17 2007-04-19 Robinson Scott H Virtual environment manager
US20070124434A1 (en) * 2005-11-29 2007-05-31 Ned Smith Network access control for many-core systems
US20080104589A1 (en) * 2006-11-01 2008-05-01 Mccrory Dave Dennis Adaptive, Scalable I/O Request Handling Architecture in Virtualized Computer Systems and Networks
US20080104591A1 (en) * 2006-11-01 2008-05-01 Mccrory Dave Dennis Adaptive, Scalable I/O Request Handling Architecture in Virtualized Computer Systems and Networks
US20080162805A1 (en) * 2007-01-03 2008-07-03 Springfield Randall S Method and Apparatus for Using Non-Addressable Memories of a Computer System
US20080177993A1 (en) * 2006-08-08 2008-07-24 International Business Machines Corporation System, method and program product for control of sequencing of data processing by different programs
US20090193122A1 (en) * 2008-01-29 2009-07-30 International Business Machines Corporation Methods and systems for migrating network resources to improve network utilization
US20090198899A1 (en) * 2008-01-31 2009-08-06 Bea Systems, Inc. System and method for transactional cache
US20090216929A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation System, method and computer program product for providing a programmable quiesce filtering register
US20090216995A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation System, method and computer program product for providing quiesce filtering for shared memory
US20090217264A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation Method, system and computer program product for providing filtering of guest2 quiesce requests
US20090216963A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation System, method and computer program product for providing a shared memory translation facility
US20100057741A1 (en) * 2008-08-29 2010-03-04 International Business Management Productions Software resource access utilizing multiple lock tables
US20100070732A1 (en) * 2008-09-15 2010-03-18 International Business Machines Corporation Apparatus and method for provisioning storage to a shared file system in a storage area network
US20100138612A1 (en) * 2007-08-01 2010-06-03 Hangzhou H3C Technologies Co., Ltd. System and method for implementing cache sharing
US20100287339A1 (en) * 2009-05-08 2010-11-11 International Business Machines Corporation Demand based partitioning or microprocessor caches
US20110289501A1 (en) * 2009-02-27 2011-11-24 Fujitsu Limited Information processing device, information processing method, and storage medium storing computer program
US20120137062A1 (en) * 2010-11-30 2012-05-31 International Business Machines Corporation Leveraging coalesced memory
US8255922B1 (en) * 2006-01-09 2012-08-28 Oracle America, Inc. Mechanism for enabling multiple processes to share physical memory
WO2014078823A1 (en) * 2012-11-19 2014-05-22 Marvell World Trade Ltd. Locally caching data from a shared storage
US20140281131A1 (en) * 2013-03-15 2014-09-18 Fusion-Io, Inc. Systems and methods for persistent cache logging
US20140337847A1 (en) * 2011-10-25 2014-11-13 Fujitsu Technology Solutions Intellectual Property Gmbh Cluster system and method for executing a plurality of virtual machines
US8898418B2 (en) 2008-08-26 2014-11-25 International Business Machines Corporation Method, apparatus and computer program for provisioning a storage volume to a virtual server
US8904113B2 (en) 2012-05-24 2014-12-02 International Business Machines Corporation Virtual machine exclusive caching
US20150058926A1 (en) * 2013-08-23 2015-02-26 International Business Machines Corporation Shared Page Access Control Among Cloud Objects In A Distributed Cloud Environment
US20160314076A1 (en) * 2007-11-16 2016-10-27 Vmware, Inc. Vm inter-process communication
US9600185B2 (en) * 2012-12-13 2017-03-21 Hitachi, Ltd. Computer realizing high-speed access and data protection of storage device, computer system, and I/O request processing method

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7257811B2 (en) * 2004-05-11 2007-08-14 International Business Machines Corporation System, method and program to migrate a virtual machine
US20070179807A1 (en) * 2006-02-01 2007-08-02 Cerner Innovation, Inc. Order profile safeguarding mechanism
US20090037915A1 (en) * 2007-07-31 2009-02-05 Rothman Michael A Staging block-based transactions
US8015115B2 (en) * 2007-12-27 2011-09-06 Pitney Bowes Inc. System and method for providing controlled access to a funds dispensing device from external processors
US8700727B1 (en) * 2010-02-05 2014-04-15 Toshiba Corporation Peer-to-peer based caching for network file system
US8863117B2 (en) * 2010-07-19 2014-10-14 International Business Machines Corporation Optimizing a file system interface in a virtualized computing environment
US8463788B2 (en) 2010-09-03 2013-06-11 Marvell World Trade Ltd. Balancing caching load in a peer-to-peer based network file system
US20120089650A1 (en) * 2010-10-08 2012-04-12 Spectra Logic Corporation System and method for a storage system
US8468524B2 (en) * 2010-10-13 2013-06-18 Lsi Corporation Inter-virtual machine time profiling of I/O transactions
US9003104B2 (en) 2011-02-15 2015-04-07 Intelligent Intellectual Property Holdings 2 Llc Systems and methods for a file-level cache
US8996807B2 (en) 2011-02-15 2015-03-31 Intelligent Intellectual Property Holdings 2 Llc Systems and methods for a multi-level cache
US8874823B2 (en) 2011-02-15 2014-10-28 Intellectual Property Holdings 2 Llc Systems and methods for managing data input/output operations
US9201677B2 (en) 2011-05-23 2015-12-01 Intelligent Intellectual Property Holdings 2 Llc Managing data input/output operations
US9116812B2 (en) 2012-01-27 2015-08-25 Intelligent Intellectual Property Holdings 2 Llc Systems and methods for a de-duplication cache
US9612966B2 (en) 2012-07-03 2017-04-04 Sandisk Technologies Llc Systems, methods and apparatus for a virtual machine cache
US9086957B2 (en) 2012-08-02 2015-07-21 International Business Machines Corporation Requesting a memory space by a memory controller
US9524190B1 (en) * 2012-09-07 2016-12-20 Veritas Technologies, LLC Systems and methods for caching data on virtualization servers
US9740563B2 (en) * 2013-05-24 2017-08-22 International Business Machines Corporation Controlling software processes that are subject to communications restrictions by freezing and thawing a computational process in a virtual machine from writing data
US9652270B2 (en) 2014-03-21 2017-05-16 Intel Corporation Apparatus and method for virtualized computing
US9710381B2 (en) 2014-06-18 2017-07-18 International Business Machines Corporation Method and apparatus for cache memory data processing
US9389789B2 (en) 2014-12-15 2016-07-12 International Business Machines Corporation Migration of executing applications and associated stored data

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4965719A (en) * 1988-02-16 1990-10-23 International Business Machines Corporation Method for lock management, page coherency, and asynchronous writing of changed pages to shared external store in a distributed computing system
US5713008A (en) * 1995-06-08 1998-01-27 Sun Microsystems Determination of working sets by logging and simulating filesystem operations
US6075938A (en) * 1997-06-10 2000-06-13 The Board Of Trustees Of The Leland Stanford Junior University Virtual machine monitors for scalable multiprocessors
US6170045B1 (en) * 1997-04-30 2001-01-02 International Business Machines Corporation Cross-system data piping using an external shared memory
US6314501B1 (en) * 1998-07-23 2001-11-06 Unisys Corporation Computer system and method for operating multiple operating systems in different partitions of the computer system and for allowing the different partitions to communicate with one another through shared memory
US6389482B1 (en) * 1997-08-28 2002-05-14 International Business Machines Corp. Dynamic transitioning from a local pipe to a cross-system pipe
US20020099765A1 (en) * 2001-01-23 2002-07-25 Otis Allen J. Generational garbage collector with persistent object cache
US6496909B1 (en) * 1999-04-06 2002-12-17 Silicon Graphics, Inc. Method for managing concurrent access to virtual memory data structures
US6542926B2 (en) * 1998-06-10 2003-04-01 Compaq Information Technologies Group, L.P. Software partitioned multi-processor system with flexible resource sharing levels
US6738977B1 (en) * 2000-05-31 2004-05-18 International Business Machines Corporation Class sharing between multiple virtual machines

Family Cites Families (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS61206043A (en) 1985-03-11 1986-09-12 Hitachi Ltd Interruption control method in virtual computer system
US4835685A (en) 1985-05-06 1989-05-30 Computer X, Inc. Virtual single machine with message-like hardware interrupts and processor exceptions
JPS6336445A (en) 1986-07-31 1988-02-17 Nec Corp File sharing control system in virtual computer system
JPH02112055A (en) 1988-10-21 1990-04-24 Fuji Electric Co Ltd Data transfer system for multiprocessor system
CA2027934C (en) 1989-12-22 1994-06-21 Cherie C. Barnes Accelerated deadlock detection in congested data transactions
JPH04367963A (en) 1991-06-15 1992-12-21 Hitachi Ltd Shared storage communication system
JPH0619785A (en) 1992-03-27 1994-01-28 Matsushita Electric Ind Co Ltd Distributed shared virtual memory and its constitution method
JPH0713823A (en) 1993-06-24 1995-01-17 Nec Corp File resource management system of virtual computer system
JP3696901B2 (en) 1994-07-19 2005-09-21 キヤノン株式会社 Load balancing method
US5884077A (en) 1994-08-31 1999-03-16 Canon Kabushiki Kaisha Information processing system and method in which computer with high load borrows processor of computer with low load to execute process
JP3512910B2 (en) 1995-07-06 2004-03-31 株式会社東芝 Storage space management method in a distributed computer system, the computer and data transfer method
US5794044A (en) * 1995-12-08 1998-08-11 Sun Microsystems, Inc. System and method for runtime optimization of private variable function calls in a secure interpreter
JPH09319653A (en) 1996-05-31 1997-12-12 Canon Inc Information processor, information processing system and control method for the same
US5953538A (en) 1996-11-12 1999-09-14 Digital Equipment Corporation Method and apparatus providing DMA transfers between devices coupled to different host bus bridges
US6438663B1 (en) 1996-12-11 2002-08-20 Steeleye Technology, Inc. System and method for identifying shared virtual memory in a computer cluster
FR2763714B1 (en) 1997-05-26 1999-07-02 Bull Sa Replacement Counters machine has nonuniform memory access
US6003066A (en) 1997-08-14 1999-12-14 International Business Machines Corporation System for distributing a plurality of threads associated with a process initiating by one data processing station among data processing stations
US6205528B1 (en) 1997-08-29 2001-03-20 International Business Machines Corporation User specifiable allocation of memory for processes in a multiprocessor computer having a non-uniform memory architecture
JPH11149387A (en) 1997-11-17 1999-06-02 Hitachi Ltd Common device control method and its implementing device
US6332180B1 (en) 1998-06-10 2001-12-18 Compaq Information Technologies Group, L.P. Method and apparatus for communication in a multi-processor computer system
US6601146B2 (en) 1998-06-16 2003-07-29 International Business Machines Corporation Technique for efficiently transferring moderate amounts of data across address space boundary
US6154832A (en) 1998-12-04 2000-11-28 Advanced Micro Devices, Inc. Processor employing multiple register sets to eliminate interrupts
US6115779A (en) 1999-01-21 2000-09-05 Advanced Micro Devices, Inc. Interrupt management system having batch mechanism for handling interrupt events
US6397350B1 (en) 1999-02-19 2002-05-28 International Business Machines Corporation Method of providing direct data processing access using a queued direct input-output device
US6347341B1 (en) 1999-02-22 2002-02-12 International Business Machines Corporation Computer program product used for exchange and transfer of data having a siga vector and utilizing a queued direct input-output device
WO2000073902A1 (en) 1999-06-01 2000-12-07 Microsoft Corporation Single logical clipboard for multiple computers
WO2000079302A1 (en) 1999-06-21 2000-12-28 Kirov Assen S Three-dimensional liquid scintillation dosimetry system
JP2002073358A (en) 2000-09-04 2002-03-12 Hitachi Ltd Method for access and control of logical partitioning memory
GB2381092B (en) 2001-10-19 2005-10-19 Ibm Object locking in a shared VM environment
US7131120B2 (en) 2002-05-16 2006-10-31 Sun Microsystems, Inc. Inter Java virtual machine (JVM) resource locking mechanism
US7181744B2 (en) 2002-10-24 2007-02-20 International Business Machines Corporation System and method for transferring data between virtual machines or other computer entities
US7299468B2 (en) 2003-04-29 2007-11-20 International Business Machines Corporation Management of virtual machines to utilize shared resources
US7251815B2 (en) 2003-04-29 2007-07-31 International Business Machines Corporation Multiple virtual machines sharing processor and work queue in memory having program/dispatch functions for assigning and accessing work items while the virtual machine was not idle

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4965719A (en) * 1988-02-16 1990-10-23 International Business Machines Corporation Method for lock management, page coherency, and asynchronous writing of changed pages to shared external store in a distributed computing system
US5713008A (en) * 1995-06-08 1998-01-27 Sun Microsystems Determination of working sets by logging and simulating filesystem operations
US6170045B1 (en) * 1997-04-30 2001-01-02 International Business Machines Corporation Cross-system data piping using an external shared memory
US6075938A (en) * 1997-06-10 2000-06-13 The Board Of Trustees Of The Leland Stanford Junior University Virtual machine monitors for scalable multiprocessors
US6389482B1 (en) * 1997-08-28 2002-05-14 International Business Machines Corp. Dynamic transitioning from a local pipe to a cross-system pipe
US6542926B2 (en) * 1998-06-10 2003-04-01 Compaq Information Technologies Group, L.P. Software partitioned multi-processor system with flexible resource sharing levels
US6314501B1 (en) * 1998-07-23 2001-11-06 Unisys Corporation Computer system and method for operating multiple operating systems in different partitions of the computer system and for allowing the different partitions to communicate with one another through shared memory
US20030037178A1 (en) * 1998-07-23 2003-02-20 Vessey Bruce Alan System and method for emulating network communications between partitions of a computer system
US6496909B1 (en) * 1999-04-06 2002-12-17 Silicon Graphics, Inc. Method for managing concurrent access to virtual memory data structures
US6738977B1 (en) * 2000-05-31 2004-05-18 International Business Machines Corporation Class sharing between multiple virtual machines
US20020099765A1 (en) * 2001-01-23 2002-07-25 Otis Allen J. Generational garbage collector with persistent object cache

Cited By (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050132363A1 (en) * 2003-12-16 2005-06-16 Vijay Tewari Method, apparatus and system for optimizing context switching between virtual machines
US20070089111A1 (en) * 2004-12-17 2007-04-19 Robinson Scott H Virtual environment manager
US10019273B2 (en) 2004-12-17 2018-07-10 Intel Corporation Virtual environment manager
US9606821B2 (en) 2004-12-17 2017-03-28 Intel Corporation Virtual environment manager for creating and managing virtual machine environments
US20070124434A1 (en) * 2005-11-29 2007-05-31 Ned Smith Network access control for many-core systems
US20120226825A1 (en) * 2005-11-29 2012-09-06 Ned Smith Network access control for many-core systems
US8930580B2 (en) * 2005-11-29 2015-01-06 Intel Corporation Network access control for many-core systems
US8180923B2 (en) * 2005-11-29 2012-05-15 Intel Corporation Network access control for many-core systems
US8255922B1 (en) * 2006-01-09 2012-08-28 Oracle America, Inc. Mechanism for enabling multiple processes to share physical memory
US20080177993A1 (en) * 2006-08-08 2008-07-24 International Business Machines Corporation System, method and program product for control of sequencing of data processing by different programs
US8001540B2 (en) 2006-08-08 2011-08-16 International Business Machines Corporation System, method and program product for control of sequencing of data processing by different programs
US20080104589A1 (en) * 2006-11-01 2008-05-01 Mccrory Dave Dennis Adaptive, Scalable I/O Request Handling Architecture in Virtualized Computer Systems and Networks
US7529867B2 (en) 2006-11-01 2009-05-05 Inovawave, Inc. Adaptive, scalable I/O request handling architecture in virtualized computer systems and networks
US20080104591A1 (en) * 2006-11-01 2008-05-01 Mccrory Dave Dennis Adaptive, Scalable I/O Request Handling Architecture in Virtualized Computer Systems and Networks
US20080162805A1 (en) * 2007-01-03 2008-07-03 Springfield Randall S Method and Apparatus for Using Non-Addressable Memories of a Computer System
US20100138612A1 (en) * 2007-08-01 2010-06-03 Hangzhou H3C Technologies Co., Ltd. System and method for implementing cache sharing
US20160314076A1 (en) * 2007-11-16 2016-10-27 Vmware, Inc. Vm inter-process communication
US9940263B2 (en) * 2007-11-16 2018-04-10 Vmware, Inc. VM inter-process communication
US9141437B2 (en) 2008-01-29 2015-09-22 International Business Machines Corporation Methods and systems for migrating network resources to improve network utilization
US20090193122A1 (en) * 2008-01-29 2009-07-30 International Business Machines Corporation Methods and systems for migrating network resources to improve network utilization
US8700855B2 (en) 2008-01-31 2014-04-15 Oracle International Corporation System and method for supporting a tiered cache
US20090198899A1 (en) * 2008-01-31 2009-08-06 Bea Systems, Inc. System and method for transactional cache
US8019945B2 (en) 2008-01-31 2011-09-13 Oracle International Corporation System and method for transactional cache
US20090216929A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation System, method and computer program product for providing a programmable quiesce filtering register
US20090216963A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation System, method and computer program product for providing a shared memory translation facility
US8140834B2 (en) 2008-02-26 2012-03-20 International Business Machines Corporation System, method and computer program product for providing a programmable quiesce filtering register
US20090217264A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation Method, system and computer program product for providing filtering of guest2 quiesce requests
US8332614B2 (en) 2008-02-26 2012-12-11 International Business Machines Corporation System, method and computer program product for providing a programmable quiesce filtering register
US8380907B2 (en) 2008-02-26 2013-02-19 International Business Machines Corporation Method, system and computer program product for providing filtering of GUEST2 quiesce requests
US8862834B2 (en) * 2008-02-26 2014-10-14 International Business Machines Corporation Shared memory translation facility
US8458438B2 (en) 2008-02-26 2013-06-04 International Business Machines Corporation System, method and computer program product for providing quiesce filtering for shared memory
US8527715B2 (en) * 2008-02-26 2013-09-03 International Business Machines Corporation Providing a shared memory translation facility
US20090216995A1 (en) * 2008-02-26 2009-08-27 International Business Machines Corporation System, method and computer program product for providing quiesce filtering for shared memory
US8898418B2 (en) 2008-08-26 2014-11-25 International Business Machines Corporation Method, apparatus and computer program for provisioning a storage volume to a virtual server
US20100057741A1 (en) * 2008-08-29 2010-03-04 International Business Management Productions Software resource access utilizing multiple lock tables
US8996835B2 (en) 2008-09-15 2015-03-31 International Business Machines Corporation Apparatus and method for provisioning storage to a shared file system in a storage area network
US20100070732A1 (en) * 2008-09-15 2010-03-18 International Business Machines Corporation Apparatus and method for provisioning storage to a shared file system in a storage area network
US20110289501A1 (en) * 2009-02-27 2011-11-24 Fujitsu Limited Information processing device, information processing method, and storage medium storing computer program
US8458401B2 (en) 2009-05-08 2013-06-04 International Business Machines Corporation Demand based partitioning of microprocessor caches
US8447929B2 (en) 2009-05-08 2013-05-21 International Business Machines Corporation Demand based partitioning of microprocessor caches
US8195879B2 (en) 2009-05-08 2012-06-05 International Business Machines Corporation Demand based partitioning of microprocessor caches
US20100287339A1 (en) * 2009-05-08 2010-11-11 International Business Machines Corporation Demand based partitioning or microprocessor caches
US20120137062A1 (en) * 2010-11-30 2012-05-31 International Business Machines Corporation Leveraging coalesced memory
US20140337847A1 (en) * 2011-10-25 2014-11-13 Fujitsu Technology Solutions Intellectual Property Gmbh Cluster system and method for executing a plurality of virtual machines
US8904113B2 (en) 2012-05-24 2014-12-02 International Business Machines Corporation Virtual machine exclusive caching
WO2014078823A1 (en) * 2012-11-19 2014-05-22 Marvell World Trade Ltd. Locally caching data from a shared storage
US9405689B2 (en) 2012-11-19 2016-08-02 Marvell World Trade Ltd. Locally caching data from a shared storage
US9600185B2 (en) * 2012-12-13 2017-03-21 Hitachi, Ltd. Computer realizing high-speed access and data protection of storage device, computer system, and I/O request processing method
US20140281131A1 (en) * 2013-03-15 2014-09-18 Fusion-Io, Inc. Systems and methods for persistent cache logging
US9842053B2 (en) * 2013-03-15 2017-12-12 Sandisk Technologies Llc Systems and methods for persistent cache logging
US20150058926A1 (en) * 2013-08-23 2015-02-26 International Business Machines Corporation Shared Page Access Control Among Cloud Objects In A Distributed Cloud Environment

Also Published As

Publication number Publication date Type
US7831977B2 (en) 2010-11-09 grant
JP2004326753A (en) 2004-11-18 application
US20100299673A1 (en) 2010-11-25 application
JP4012517B2 (en) 2007-11-21 grant
US8589937B2 (en) 2013-11-19 grant

Similar Documents

Publication Publication Date Title
US8930947B1 (en) System and method for live migration of a virtual machine with dedicated cache
US5261088A (en) Managing locality in space reuse in a shadow written B-tree via interior node free space list
Fitzgerald et al. The integration of virtual memory management and interprocess communication in accent
US6925515B2 (en) Producer/consumer locking system for efficient replication of file data
US7647443B1 (en) Implementing I/O locks in storage systems with reduced memory and performance costs
US5317728A (en) Storage management of a first file system using a second file system containing surrogate files and catalog management information
US5301290A (en) Method for minimizing lock processing while ensuring consistency among pages common to local processor caches and a shared external store
US7409487B1 (en) Virtualization system for computers that use address space indentifiers
US6804729B2 (en) Migrating a memory page by modifying a page migration state of a state machine associated with a DMA mapper based on a state notification from an operating system kernel
Meyer et al. Parallax: virtual disks for virtual machines
US20080140937A1 (en) System and Methodology Providing Multiple Heterogeneous Buffer Caches
US5946711A (en) System for locking data in a shared cache
US7584222B1 (en) Methods and apparatus facilitating access to shared storage among multiple computers
US5410697A (en) Concurrency management using version identification of shared data as a supplement to use of locks
US7380039B2 (en) Apparatus, method and system for aggregrating computing resources
US8805951B1 (en) Virtual machines and cloud storage caching for cloud computing applications
US20050086237A1 (en) Shared queues in shared object space
US20050193160A1 (en) Database System Providing Methodology for Extended Memory Support
US20120011508A1 (en) Multiple time granularity support for online classification of memory pages based on activity level
US20090271418A1 (en) Computer file system with path lookup tables
US5842226A (en) Virtual memory management for a microkernel system with multiple operating systems
US7010554B2 (en) Delegation of metadata management in a storage system by leasing of free file system blocks and i-nodes from a file system owner
US9235524B1 (en) System and method for improving cache performance
US20040044643A1 (en) Managing multiple virtual machines
US20090327576A1 (en) Direct Memory Access Filter for Virtualized Operating Systems

Legal Events

Date Code Title Description
AS Assignment

Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:SHULTZ, STEVEN;TKATSCHOW, XENIA;REEL/FRAME:016399/0461

Effective date: 20050606

REMI Maintenance fee reminder mailed
FPAY Fee payment

Year of fee payment: 4

SULP Surcharge for late payment
FEPP

Free format text: MAINTENANCE FEE REMINDER MAILED (ORIGINAL EVENT CODE: REM.)